Quality of Synthetic Speech Perceptual Dimensions, Influencing Factors, and Instrumental Assessment

This book reviews research towards perceptual quality dimensions of synthetic speech, compares these findings with the state of the art, and derives a set of five universal perceptual quality dimensions for TTS signals. They are: (i) naturalness of voice, (ii) prosodic quality, (iii) fluency and int...

Full description

Bibliographic Details
Main Author: Hinterleitner, Florian
Format: eBook
Language:English
Published: Singapore Springer Nature Singapore 2017, 2017
Edition:1st ed. 2017
Series:T-Labs Series in Telecommunication Services
Subjects:
Online Access:
Collection: Springer eBooks 2005- - Collection details see MPG.ReNa
LEADER 02277nmm a2200313 u 4500
001 EB001419716
003 EBX01000000000000000911720
005 00000000000000.0
007 cr|||||||||||||||||||||
008 170502 ||| eng
020 |a 9789811037344 
100 1 |a Hinterleitner, Florian 
245 0 0 |a Quality of Synthetic Speech  |h Elektronische Ressource  |b Perceptual Dimensions, Influencing Factors, and Instrumental Assessment  |c by Florian Hinterleitner 
250 |a 1st ed. 2017 
260 |a Singapore  |b Springer Nature Singapore  |c 2017, 2017 
300 |a XVI, 157 p. 29 illus  |b online resource 
505 0 |a Introduction -- Speech Synthesis -- Auditory and Instrumental Quality Evaluation Metrics -- Perceptual Quality Dimensions -- Influencing Factors on Perceptual Quality -- Instrumental Quality Assessment -- Requirements for the Integration of an Instrumental Quality Measure into a Concatenative TTS System -- Conclusions 
653 |a User interfaces (Computer systems) 
653 |a Signal, Speech and Image Processing 
653 |a Signal processing 
653 |a User Interfaces and Human Computer Interaction 
653 |a Human-computer interaction 
041 0 7 |a eng  |2 ISO 639-2 
989 |b Springer  |a Springer eBooks 2005- 
490 0 |a T-Labs Series in Telecommunication Services 
028 5 0 |a 10.1007/978-981-10-3734-4 
856 4 0 |u https://doi.org/10.1007/978-981-10-3734-4?nosfx=y  |x Verlag  |3 Volltext 
082 0 |a 621.382 
520 |a This book reviews research towards perceptual quality dimensions of synthetic speech, compares these findings with the state of the art, and derives a set of five universal perceptual quality dimensions for TTS signals. They are: (i) naturalness of voice, (ii) prosodic quality, (iii) fluency and intelligibility, (iv) absence of disturbances, and (v) calmness. Moreover, a test protocol for the efficient indentification of those dimensions in a listening test is introduced. Furthermore, several factors influencing these dimensions are examined. In addition, different techniques for the instrumental quality assessment of TTS signals are introduced, reviewed and tested. Finally, the requirements for the integration of an instrumental quality measure into a concatenative TTS system are examined